{"id":"https://openalex.org/W4221165543","doi":"https://doi.org/10.1109/icassp43922.2022.9747381","title":"The Volcspeech System for the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge","display_name":"The Volcspeech System for the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221165543","doi":"https://doi.org/10.1109/icassp43922.2022.9747381"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747381","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046864714","display_name":"Chen Shen","orcid":"https://orcid.org/0000-0003-3535-8494"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chen Shen","raw_affiliation_strings":["Bytedance AI Lab"],"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087964419","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0002-0811-6150"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Bytedance AI Lab"],"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081977221","display_name":"Wenzhi Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenzhi Fan","raw_affiliation_strings":["Bytedance AI Lab"],"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059575276","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0003-4748-6426"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Wang","raw_affiliation_strings":["Bytedance AI Lab"],"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007443927","display_name":"Shixue Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shixue Wen","raw_affiliation_strings":["Bytedance AI Lab"],"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387925","display_name":"Yao Tian","orcid":"https://orcid.org/0009-0002-3530-3944"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao Tian","raw_affiliation_strings":["Bytedance AI Lab"],"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400217","display_name":"Jun Zhang","orcid":"https://orcid.org/0000-0001-7835-9871"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Zhang","raw_affiliation_strings":["Bytedance AI Lab"],"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101153366","display_name":"Jingsheng Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingsheng Yang","raw_affiliation_strings":["Bytedance AI Lab"],"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101108160","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["Bytedance AI Lab"],"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5046864714"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5197,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.61042879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"9176","last_page":"9180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7983018159866333},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7866044044494629},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6347588896751404},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5768387913703918},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4925859570503235},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4779236912727356},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.47237494587898254},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4635225236415863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3457235097885132},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.29592669010162354},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13389000296592712}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7983018159866333},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7866044044494629},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6347588896751404},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5768387913703918},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4925859570503235},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4779236912727356},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.47237494587898254},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4635225236415863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3457235097885132},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.29592669010162354},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13389000296592712},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747381","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2291877678","https://openalex.org/W2526425061","https://openalex.org/W2696967604","https://openalex.org/W2936774411","https://openalex.org/W2949676527","https://openalex.org/W2962780374","https://openalex.org/W2963302875","https://openalex.org/W2997419692","https://openalex.org/W3013139777","https://openalex.org/W3096408984","https://openalex.org/W3097777922","https://openalex.org/W3105031100","https://openalex.org/W3115097893","https://openalex.org/W3140898556","https://openalex.org/W3143367551","https://openalex.org/W3161587262","https://openalex.org/W3178462146","https://openalex.org/W3196117288","https://openalex.org/W3198455895","https://openalex.org/W3207834622","https://openalex.org/W4205969058","https://openalex.org/W4206633762","https://openalex.org/W4224925136","https://openalex.org/W4297775537","https://openalex.org/W4385245566","https://openalex.org/W6688816777","https://openalex.org/W6737664043","https://openalex.org/W6739901393","https://openalex.org/W6775489429","https://openalex.org/W6781999463","https://openalex.org/W6784533385","https://openalex.org/W6787743207","https://openalex.org/W6787874867","https://openalex.org/W6800885585"],"related_works":["https://openalex.org/W135211875","https://openalex.org/W2052269122","https://openalex.org/W4389272081","https://openalex.org/W89843531","https://openalex.org/W4319587085","https://openalex.org/W1549221042","https://openalex.org/W3011547127","https://openalex.org/W4319586547","https://openalex.org/W2915347927","https://openalex.org/W2342291550"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3,104],"submission":[4],"to":[5,21,29,42,56,68,121,132,147,162],"ICASSP":[6],"2022":[7],"Multi-channel":[8,49],"Multi-party":[9],"Meeting":[10],"Transcription":[11],"(M2MeT)":[12],"Challenge.":[13],"For":[14,99],"Track":[15,100],"1,":[16],"we":[17,102],"propose":[18,127],"several":[19],"approaches":[20],"make":[22],"the":[23,36,44,58,70,77,83,89,96,107,138,151,172,178,185],"clustering-based":[24],"speaker":[25,47,60],"diarization":[26,97],"system":[27,105],"enable":[28],"handle":[30],"overlapped":[31,123],"speech.":[32],"Front-end":[33],"dereverberation":[34],"and":[35,51,86,136,175],"direction-of-arrival":[37],"(DOA)":[38],"estimation":[39],"are":[40,54,145],"used":[41],"improve":[43],"accuracy":[45],"of":[46,80],"diarization.":[48],"combination":[50],"overlap":[52],"detection":[53],"applied":[55],"reduce":[57],"missed":[59],"error.":[61],"A":[62],"modified":[63],"DOVER-Lap":[64],"is":[65,119,160,169],"also":[66],"proposed":[67],"fuse":[69],"results":[71],"from":[72],"different":[73],"systems.":[74],"We":[75,126],"achieve":[76,163],"final":[78,167],"DER":[79],"5.79%":[81],"on":[82,88,171,177],"Eval":[84,173],"set":[85,174],"7.23%":[87],"Test":[90,179],"set,":[91,180],"which":[92,181],"ranks":[93,182],"4th":[94],"in":[95,110,150,184],"challenge.":[98,187],"2,":[101],"develop":[103],"using":[106],"Conformer":[108],"model":[109,133,139,158],"a":[111,128],"joint":[112],"CTC-attention":[113],"architecture.":[114],"Serialized":[115],"output":[116],"training":[117],"(SOT)":[118],"adopted":[120],"multi-speaker":[122,153],"speech":[124],"recognition.":[125],"neural":[129],"front-end":[130],"module":[131],"multi-channel":[134,152],"audio":[135],"train":[137],"end-to-end.":[140],"Various":[141],"data":[142],"augmentation":[143],"methods":[144],"utilized":[146],"mitigate":[148],"over-fitting":[149],"E2E":[154],"system.":[155],"Transformer":[156],"language":[157],"fusion":[159],"developed":[161],"better":[164],"performance.":[165],"The":[166],"CER":[168],"19.2%":[170],"20.8%":[176],"2nd":[183],"ASR":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}